Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Jiashuo, Zong, Yiming, Ye, Yinyu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.12037
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912381017260032
author Jiang, Jiashuo
Zong, Yiming
Ye, Yinyu
author_facet Jiang, Jiashuo
Zong, Yiming
Ye, Yinyu
contents Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Function approximations are usually deployed to handle large or infinite state-action space. In our work, we consider the RL problems with function approximation and we develop a new algorithm to solve it efficiently. Our algorithm is based on the linear programming (LP) reformulation and it resolves the LP at each iteration improved with new data arrival. Such a resolving scheme enables our algorithm to achieve an instance-dependent sample complexity guarantee, more precisely, when we have $N$ data, the output of our algorithm enjoys an instance-dependent $\tilde{O}(1/N)$ suboptimality gap. In comparison to the $O(1/\sqrt{N})$ worst-case guarantee established in the previous literature, our instance-dependent guarantee is tighter when the underlying instance is favorable, and the numerical experiments also reveal the efficient empirical performances of our algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Resolving Methods for Reinforcement Learning with Function Approximations
Jiang, Jiashuo
Zong, Yiming
Ye, Yinyu
Machine Learning
Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Function approximations are usually deployed to handle large or infinite state-action space. In our work, we consider the RL problems with function approximation and we develop a new algorithm to solve it efficiently. Our algorithm is based on the linear programming (LP) reformulation and it resolves the LP at each iteration improved with new data arrival. Such a resolving scheme enables our algorithm to achieve an instance-dependent sample complexity guarantee, more precisely, when we have $N$ data, the output of our algorithm enjoys an instance-dependent $\tilde{O}(1/N)$ suboptimality gap. In comparison to the $O(1/\sqrt{N})$ worst-case guarantee established in the previous literature, our instance-dependent guarantee is tighter when the underlying instance is favorable, and the numerical experiments also reveal the efficient empirical performances of our algorithms.
title Adaptive Resolving Methods for Reinforcement Learning with Function Approximations
topic Machine Learning
url https://arxiv.org/abs/2505.12037